Predictive Capability of QSAR Models Based on the CompTox Zebrafish Embryo Assays: An Imbalanced Classification Problem.

The CompTox Chemistry Dashboard (ToxCast) contains one of the largest public databases on Zebrafish (Danio rerio) developmental toxicity. The data consists of 19 toxicological endpoints on unique 1018 compounds measured in relatively low concentration ranges. The endpoints are related to developmental effects occurring in dechorionated zebrafish embryos for 120 hours post fertilization and monitored via gross malformations and mortality. We report the predictive capability of 209 quantitative structure-activity relationship (QSAR) models developed by machine learning methods using penalization techniques and diverse model quality metrics to cope with the imbalanced endpoints. All these QSAR models were generated to test how the imbalanced classification (toxic or non-toxic) endpoints could be predicted regardless which of three algorithms is used: logistic regression, multi-layer perceptron, or random forests. Additionally, QSAR toxicity models are developed starting from sets of classical molecular descriptors, structural fingerprints and their combinations. Only 8 out of 209 models passed the 0.20 Matthew's correlation coefficient value defined a priori as a threshold for acceptable model quality on the test sets. The best models were obtained for endpoints mortality (MORT), ActivityScore and JAW (deformation). The low predictability of the QSAR model developed from the zebrafish embryotoxicity data in the database is mainly due to a higher sensitivity of 19 measurements of endpoints carried out on dechorionated embryos at low concentrations.

Discovery and pharmacological characterization of a small-molecule antagonist at neuromedin U receptor NMUR2.

Neuromedin U (NMU), through its cognate receptor NMUR2 in the central nervous system, regulates several important physiological functions, including energy balance, stress response, and nociception. By random screening of our corporate compound collection with a ligand binding assay, we discovered (R)-5'-(phenylaminocarbonylamino)spiro[1-azabicyclo[2.2.2]octane-3,2'(3'H)-furo[2,3-b]pyridine] (R-PSOP), a highly potent and selective NMUR2 antagonist. R-PSOP is a nonpeptidic small-molecule with the chemical composition C(20)N(4)O(2)H(22). In competition binding experiments, this compound was found to bind to NMUR2 with high affinity; the K(i) values were determined to be 52 and 32 nM for the human and rat NMUR2, respectively. Moreover, in functional assays measuring phosphoinositide turnover or intracellular calcium mobilization, R-PSOP strongly inhibited the responses stimulated by peptide agonists NMU-25, NMU-23, and NMU-8 in human embryonic kidney 293 cells expressing NMUR2. From Schild analyses, the functional K(b) values for R-PSOP were determined to be 92 and 155 nM at human and rat NMUR2, respectively. Highly selective for NMUR2, R-PSOP exhibited low affinity to the other subtype of NMU receptor, NMUR1, with a K(i) value >10 microM. R-PSOP in vivo attenuated NMU-23-evoked nociceptive responses in a rat spinal reflex preparation. To our knowledge, this is the first antagonist ever reported for NMU receptors. This compound could serve as a valuable tool for further understanding the physiological and pathophysiological roles of NMU system, while providing a chemical starting point that may lead to development of new therapeutics for treatment of eating disorders, obesity, pain, and stress-related disorders.